{"id":125565,"date":"2021-07-27T17:23:16","date_gmt":"2021-07-28T00:23:16","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2021\/07\/deepminds-epistemic-neural-networks-open-new-avenues-for-uncertainty-modelling-in-large-and-complex-dl-systems"},"modified":"2021-07-27T17:23:16","modified_gmt":"2021-07-28T00:23:16","slug":"deepminds-epistemic-neural-networks-open-new-avenues-for-uncertainty-modelling-in-large-and-complex-dl-systems","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2021\/07\/deepminds-epistemic-neural-networks-open-new-avenues-for-uncertainty-modelling-in-large-and-complex-dl-systems","title":{"rendered":"DeepMind\u2019s Epistemic Neural Networks Open New Avenues for Uncertainty Modelling in Large and Complex DL Systems"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/deepminds-epistemic-neural-networks-open-new-avenues-for-uncertainty-modelling-in-large-and-complex-dl-systems2.jpg\"><\/a><\/p>\n<p>Although effective uncertainty estimation can be a key consideration in the development of safe and fair artificial intelligence systems, most of today\u2019s large-scale deep learning applications are lacking in this regard.<\/p>\n<p>To accelerate research in this field, a team from DeepMind has proposed epistemic neural networks (ENNs) as an interface for uncertainty modelling in deep learning, and the KL divergence from a target distribution as a precise metric to evaluate ENNs. In the paper <em>Epistemic Neural Networks<\/em>, the team also introduces a computational testbed based on inference in a neural network Gaussian process, and validates that the proposed ENNs can improve performance in terms of statistical quality and computational cost.<\/p>\n<p>The researchers say all existing approaches to uncertainty modelling in deep learning can be expressed as ENNs, presenting a new perspective on the potential of neural networks as computational tools for approximate posterior inference.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Although effective uncertainty estimation can be a key consideration in the development of safe and fair artificial intelligence systems, most of today\u2019s large-scale deep learning applications are lacking in this regard. To accelerate research in this field, a team from DeepMind has proposed epistemic neural networks (ENNs) as an interface for uncertainty modelling in deep [\u2026]<\/p>\n","protected":false},"author":396,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-125565","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/125565","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/396"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=125565"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/125565\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=125565"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=125565"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=125565"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}